{"id":24728,"date":"2026-01-13T12:08:59","date_gmt":"2026-01-13T17:08:59","guid":{"rendered":"https:\/\/cnr.ncsu.edu\/geospatial\/?p=24728"},"modified":"2026-01-13T12:19:34","modified_gmt":"2026-01-13T17:19:34","slug":"tracking-forest-change-with-big-data","status":"publish","type":"post","link":"https:\/\/cnr.ncsu.edu\/geospatial\/news\/2026\/01\/13\/tracking-forest-change-with-big-data\/","title":{"rendered":"Tracking Forest Change with Big Data"},"content":{"rendered":"\n\n\n\n\n

Editor\u2019s note:<\/em><\/strong> Each semester, students in the <\/em>Geospatial Analytics Ph.D. program<\/em><\/a> can apply for a Geospatial Analytics Travel Award that supports research travel or presentations at conferences. <\/em>The following is a guest post by travel award winner<\/em><\/strong> <\/em>Keyu Wan<\/em><\/strong> <\/em><\/strong>as part of the <\/em>Student Travel series<\/em><\/a>.<\/em><\/p>\n\n\n\n

Forests do not disappear overnight. In many places, change happens gradually\u2014one small clearing, a new road, or a subtle shift in land use\u2014often going unnoticed until the cumulative impact becomes severe. In December 2025, I traveled to the IEEE International Conference on Big Data <\/a>in Macau, China to present my research on how satellite data and machine learning can help detect these changes more effectively and more accurately. The experience allowed me to share my work while learning from a global community of data scientists and researchers.<\/p>\n\n\n\n

At the conference, I presented a paper titled \u201cComparative Evaluation of Deep Learning Models for Large-Scale Deforestation Mapping.\u201d My research uses large volumes of satellite imagery from the Sentinel-2 mission to analyze forest change across different regions of the world. These satellites continuously observe Earth\u2019s surface, producing massive amounts of data over time. While this offers unprecedented opportunities for environmental monitoring, it also raises a key challenge: how to transform complex satellite images into reliable information that can support conservation efforts and policy decisions.<\/p>\n\n\n\n

My work addresses two closely related goals: First, it compares how different deep learning models perform in detecting deforestation within a given region. Second, it examines whether models trained in one region can successfully detect deforestation in another. This is especially important because forests in different regions differ greatly in climate, vegetation, and land-use patterns, yet effective monitoring systems must operate reliably across all of them. By evaluating multiple models across diverse landscapes, my study emphasizes the importance of methods that are not only accurate but also robust and transferable.<\/p>\n\n\n\n

\"A
Keyu Wan presents her research at the conference.<\/figcaption><\/figure>\n\n\n\n

The conference brought together participants from both academia and industry, creating a rich environment for exchanging ideas and knowledge. By listening to presentations and engaging in face-to-face discussions, I gained a clearer understanding of current research trends in big data and artificial intelligence. Conversations with industry practitioners were particularly valuable, as they highlighted how academic research can be translated into real-world applications. Together, these interactions helped me better appreciate the practical value of scientific research and its potential impact beyond the laboratory.<\/p>\n\n\n\n

Beyond the technical sessions, the conference also offered meaningful opportunities for cultural and academic exchange. A conference dinner provided a relaxed setting for informal conversations across disciplines, while a guided visit to the University of Macau showcased local research facilities and academic initiatives. Learning about different educational systems and research environments broadened my perspective and underscored the importance of international collaboration in addressing global challenges such as environmental change.<\/p>\n\n\n\n

The CGA Travel Award enabled me to participate in this international conference and engage with a diverse research community. I returned with fresh motivation, a deeper understanding of both academic and applied research directions, and new ideas for strengthening my work. Most importantly, the experience reinforced why this research matters: when used thoughtfully, big data can help us better understand our planet\u2014and support more informed decisions about its future.<\/p>\n","protected":false,"raw":"\n\n\n\n\n

Editor\u2019s note:<\/em><\/strong> Each semester, students in the <\/em>Geospatial Analytics Ph.D. program<\/em><\/a> can apply for a Geospatial Analytics Travel Award that supports research travel or presentations at conferences. <\/em>The following is a guest post by travel award winner<\/em><\/strong> <\/em>Keyu Wan<\/em><\/strong> <\/em><\/strong>as part of the <\/em>Student Travel series<\/em><\/a>.<\/em><\/p>\n\n\n\n

Forests do not disappear overnight. In many places, change happens gradually\u2014one small clearing, a new road, or a subtle shift in land use\u2014often going unnoticed until the cumulative impact becomes severe. In December 2025, I traveled to the IEEE International Conference on Big Data <\/a>in Macau, China to present my research on how satellite data and machine learning can help detect these changes more effectively and more accurately. The experience allowed me to share my work while learning from a global community of data scientists and researchers.<\/p>\n\n\n\n

At the conference, I presented a paper titled \u201cComparative Evaluation of Deep Learning Models for Large-Scale Deforestation Mapping.\u201d My research uses large volumes of satellite imagery from the Sentinel-2 mission to analyze forest change across different regions of the world. These satellites continuously observe Earth\u2019s surface, producing massive amounts of data over time. While this offers unprecedented opportunities for environmental monitoring, it also raises a key challenge: how to transform complex satellite images into reliable information that can support conservation efforts and policy decisions.<\/p>\n\n\n\n

My work addresses two closely related goals: First, it compares how different deep learning models perform in detecting deforestation within a given region. Second, it examines whether models trained in one region can successfully detect deforestation in another. This is especially important because forests in different regions differ greatly in climate, vegetation, and land-use patterns, yet effective monitoring systems must operate reliably across all of them. By evaluating multiple models across diverse landscapes, my study emphasizes the importance of methods that are not only accurate but also robust and transferable.<\/p>\n\n\n\n

\"A
Keyu Wan presents her research at the conference.<\/figcaption><\/figure>\n\n\n\n

The conference brought together participants from both academia and industry, creating a rich environment for exchanging ideas and knowledge. By listening to presentations and engaging in face-to-face discussions, I gained a clearer understanding of current research trends in big data and artificial intelligence. Conversations with industry practitioners were particularly valuable, as they highlighted how academic research can be translated into real-world applications. Together, these interactions helped me better appreciate the practical value of scientific research and its potential impact beyond the laboratory.<\/p>\n\n\n\n

Beyond the technical sessions, the conference also offered meaningful opportunities for cultural and academic exchange. A conference dinner provided a relaxed setting for informal conversations across disciplines, while a guided visit to the University of Macau showcased local research facilities and academic initiatives. Learning about different educational systems and research environments broadened my perspective and underscored the importance of international collaboration in addressing global challenges such as environmental change.<\/p>\n\n\n\n

The CGA Travel Award enabled me to participate in this international conference and engage with a diverse research community. I returned with fresh motivation, a deeper understanding of both academic and applied research directions, and new ideas for strengthening my work. Most importantly, the experience reinforced why this research matters: when used thoughtfully, big data can help us better understand our planet\u2014and support more informed decisions about its future.<\/p>\n"},"excerpt":{"rendered":"

What if we could spot deforestation before it becomes irreversible? Ph.D. student Keyu Wan shared her research at the IEEE International Conference on Big Data on how satellite imagery and machine learning can reveal subtle changes that signal deforestation.<\/p>\n","protected":false},"author":152,"featured_media":24732,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"source":"","ncst_custom_author":"","ncst_show_custom_author":false,"ncst_dynamicHeaderBlockName":"ncst\/default-post-header","ncst_dynamicHeaderData":"{\"caption\":\"Geospatial Analytics Ph.D. student Keyu Wan at the IEEE International Conference on Big Data in Macau, China in December 2025\",\"displayCategoryID\":49,\"showAuthor\":false,\"showDate\":true,\"showFeaturedVideo\":false}","ncst_content_audit_freq":"","ncst_content_audit_date":"","ncst_content_audit_display":false,"ncst_backToTopFlag":"","footnotes":"","_links_to":"","_links_to_target":""},"categories":[48,49,6],"tags":[],"class_list":["post-24728","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-geospatial-analytics-phd","category-student-travel","category-student"],"displayCategory":{"term_id":49,"name":"Student Travel","slug":"student-travel","term_group":0,"term_taxonomy_id":49,"taxonomy":"category","description":"","parent":0,"count":55,"filter":"raw"},"acf":{"ncst_posts_meta_modified_date":null},"_links":{"self":[{"href":"https:\/\/cnr.ncsu.edu\/geospatial\/wp-json\/wp\/v2\/posts\/24728","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/cnr.ncsu.edu\/geospatial\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/cnr.ncsu.edu\/geospatial\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/cnr.ncsu.edu\/geospatial\/wp-json\/wp\/v2\/users\/152"}],"replies":[{"embeddable":true,"href":"https:\/\/cnr.ncsu.edu\/geospatial\/wp-json\/wp\/v2\/comments?post=24728"}],"version-history":[{"count":8,"href":"https:\/\/cnr.ncsu.edu\/geospatial\/wp-json\/wp\/v2\/posts\/24728\/revisions"}],"predecessor-version":[{"id":24740,"href":"https:\/\/cnr.ncsu.edu\/geospatial\/wp-json\/wp\/v2\/posts\/24728\/revisions\/24740"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/cnr.ncsu.edu\/geospatial\/wp-json\/wp\/v2\/media\/24732"}],"wp:attachment":[{"href":"https:\/\/cnr.ncsu.edu\/geospatial\/wp-json\/wp\/v2\/media?parent=24728"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/cnr.ncsu.edu\/geospatial\/wp-json\/wp\/v2\/categories?post=24728"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/cnr.ncsu.edu\/geospatial\/wp-json\/wp\/v2\/tags?post=24728"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}